Andy Arditi

Karma: 416

https://andyrdt.com

Unlearning via RMU is mostly shallow

Andy Arditi and bilalchughtai

23 Jul 2024 16:07 UTC

50 points

3 comments6 min readLW link

Refusal in LLMs is mediated by a single direction

Andy Arditi, Oscar Obeso, Aaquib111, wesg and Neel Nanda

27 Apr 2024 11:13 UTC

228 points

93 comments10 min readLW link

Refusal mechanisms: initial experiments with Llama-2-7b-chat

Andy Arditi and Oscar Obeso

8 Dec 2023 17:08 UTC

81 points

7 comments7 min readLW link